Use ruff and absolute imports

.github/workflows/actions.yml

@@ -14,45 +14,8 @@ env:
   default-python: "3.10"
 
 jobs:
-
-  check-code-imports:
-    name: Format import coding style
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-      - name: Set up Python ${{ env.default-python }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ env.default-python }}
-      - name: Upgrade pip, Install nox
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install nox
-      - name: Check coding style
-        run: |
-          nox --error-on-missing-interpreters --non-interactive --session format_isort
-
-  check-code-autoflake:
-    name: Format coding style with autoflake
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-      - name: Set up Python ${{ env.default-python }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ env.default-python }}
-      - name: Upgrade pip, Install nox
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install nox
-      - name: Check coding style
-        run: |
-          nox --error-on-missing-interpreters --non-interactive --session format_autoflake
-
-  check-code-formatting:
-    name: Format coding style with black
+  code-formatting:
+    name: Format and check code style
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
@@ -69,24 +32,6 @@ jobs:
         run: |
           nox --error-on-missing-interpreters --non-interactive --session format
 
-  check-coding-style:
-    name: Lint coding style
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-      - name: Set up Python ${{ env.default-python }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ env.default-python }}
-      - name: Upgrade pip, Install nox
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install nox
-      - name: Check coding style
-        run: |
-          nox --error-on-missing-interpreters --non-interactive --session lint
-
   check-static-types:
     name: Check static types
     runs-on: ubuntu-latest

fuzzing/extract_text_fuzzer.py

@@ -6,9 +6,9 @@
 
 with atheris.instrument_imports():
     from fuzzing.utils import (
-        prepare_pdfminer_fuzzing,
-        is_valid_byte_stream,
         generate_layout_parameters,
+        is_valid_byte_stream,
+        prepare_pdfminer_fuzzing,
     )
     from pdfminer.high_level import extract_text
 

fuzzing/fuzzed_data_provider.py

@@ -26,7 +26,10 @@ def ConsumeMemoryFile(self, all_data: bool = False) -> io.BytesIO:
             return io.BytesIO(self.ConsumeRandomBytes())
 
     def ConsumeOptionalIntList(
-        self, max_count: int, min: int, max: int
+        self,
+        max_count: int,
+        min: int,
+        max: int,
     ) -> Optional[List[int]]:
         if self.ConsumeBool():
             count = self.ConsumeIntInRange(0, max_count)

fuzzing/page_extraction_fuzzer.py

@@ -30,7 +30,7 @@ def fuzz_one_input(data: bytes) -> None:
                     maxpages=fdp.ConsumeIntInRange(0, 10),
                     page_numbers=fdp.ConsumeOptionalIntList(10, 0, 10),
                     laparams=generate_layout_parameters(fdp),
-                )
+                ),
             )
     except (AssertionError, PSException):
         return

fuzzing/utils.py

@@ -1,6 +1,5 @@
-"""
-Utilities shared across the various PDF fuzzing harnesses
-"""
+"""Utilities shared across the various PDF fuzzing harnesses"""
+
 import logging
 from typing import Optional
 
@@ -12,9 +11,7 @@
 
 
 def prepare_pdfminer_fuzzing() -> None:
-    """
-    Used to disable logging of the pdfminer module
-    """
+    """Used to disable logging of the pdfminer module"""
     logging.getLogger("pdfminer").setLevel(logging.CRITICAL)
 
 

noxfile.py

@@ -6,38 +6,16 @@
 PYTHON_MODULES = ["fuzzing", "pdfminer", "tools", "tests", "noxfile.py", "setup.py"]
 
 
-@nox.session
-def format_isort(session):
-    session.install("isort")
-    if "CI" in os.environ:
-        session.run("isort", "--check", *PYTHON_MODULES)
-    else:
-        session.run("isort", *PYTHON_MODULES)
-
-
-@nox.session
-def format_autoflake(session):
-    session.install("autoflake")
-    if "CI" in os.environ:
-        session.run("autoflake", "--check-diff", *PYTHON_MODULES)
-    else:
-        session.run("autoflake", "--in-place", *PYTHON_MODULES)
-
-
 @nox.session
 def format(session):
-    session.install("black<23")
+    session.install("ruff==0.5.1")
     # Format files locally with black, but only check in cicd
     if "CI" in os.environ:
-        session.run("black", "--check", *PYTHON_MODULES)
+        session.run("ruff", "check")
+        session.run("ruff", "format", "--check")
     else:
-        session.run("black", *PYTHON_MODULES)
-
-
-@nox.session
-def lint(session):
-    session.install("flake8")
-    session.run("flake8", *PYTHON_MODULES, "--count", "--statistics")
+        session.run("ruff", "check", "--fix")
+        session.run("ruff", "format")
 
 
 @nox.session
@@ -66,8 +44,20 @@ def docs(session):
     session.install("setuptools")
     session.install("-e", ".[docs]")
     session.run(
-        "python", "-m", "sphinx", "-b", "html", "docs/source", "docs/build/html"
+        "python",
+        "-m",
+        "sphinx",
+        "-b",
+        "html",
+        "docs/source",
+        "docs/build/html",
     )
     session.run(
-        "python", "-m", "sphinx", "-b", "doctest", "docs/source", "docs/build/doctest"
+        "python",
+        "-m",
+        "sphinx",
+        "-b",
+        "doctest",
+        "docs/source",
+        "docs/build/doctest",
     )

pdfminer/_saslprep.py

@@ -24,7 +24,7 @@
 import unicodedata
 from typing import Callable, Tuple
 
-from .pdfexceptions import PDFValueError
+from pdfminer.pdfexceptions import PDFValueError
 
 # RFC4013 section 2.3 prohibited output.
 _PROHIBITED: Tuple[Callable[[str], bool], ...] = (
@@ -66,7 +66,11 @@ def saslprep(data: str, prohibit_unassigned_code_points: bool = True) -> str:
     in_table_c12 = stringprep.in_table_c12
     in_table_b1 = stringprep.in_table_b1
     data = "".join(
-        ["\u0020" if in_table_c12(elt) else elt for elt in data if not in_table_b1(elt)]
+        [
+            "\u0020" if in_table_c12(elt) else elt
+            for elt in data
+            if not in_table_b1(elt)
+        ],
     )
 
     # RFC3454 section 2, step 2 - Normalize

pdfminer/arcfour.py

@@ -1,10 +1,9 @@
-""" Python implementation of Arcfour encryption algorithm.
+"""Python implementation of Arcfour encryption algorithm.
 See https://en.wikipedia.org/wiki/RC4
 This code is in the public domain.
 
 """
 
-
 from typing import Sequence
 
 

pdfminer/ascii85.py

@@ -1,4 +1,4 @@
-""" Python implementation of ASCII85/ASCIIHex decoder (Adobe version).
+"""Python implementation of ASCII85/ASCIIHex decoder (Adobe version).
 
 This code is in the public domain.
 
@@ -10,8 +10,7 @@
 
 # ascii85decode(data)
 def ascii85decode(data: bytes) -> bytes:
-    """
-    In ASCII85 encoding, every four bytes are encoded with five ASCII
+    """In ASCII85 encoding, every four bytes are encoded with five ASCII
     letters, using 85 different types of characters (as 256**4 < 85**5).
     When the length of the original bytes is not a multiple of 4, a special
     rule is used for round up.
@@ -24,7 +23,7 @@ def ascii85decode(data: bytes) -> bytes:
     out = b""
     for i in iter(data):
         c = bytes((i,))
-        if b"!" <= c and c <= b"u":
+        if c >= b"!" and c <= b"u":
             n += 1
             b = b * 85 + (ord(c) - 33)
             if n == 5:
@@ -48,8 +47,7 @@ def ascii85decode(data: bytes) -> bytes:
 
 
 def asciihexdecode(data: bytes) -> bytes:
-    """
-    ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
+    """ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
     For each pair of ASCII hexadecimal digits (0-9 and A-F or a-f), the
     ASCIIHexDecode filter produces one byte of binary data. All white-space
     characters are ignored. A right angle bracket character (>) indicates

pdfminer/ccitt.py

@@ -25,7 +25,7 @@
     cast,
 )
 
-from .pdfexceptions import PDFException, PDFValueError
+from pdfminer.pdfexceptions import PDFException, PDFValueError
 
 
 def get_bytes(data: bytes) -> Iterator[int]:
@@ -53,7 +53,7 @@ def add(cls, root: BitParserState, v: Union[int, str], bits: str) -> None:
         p: BitParserState = root
         b = None
         for i in range(len(bits)):
-            if 0 < i:
+            if i > 0:
                 assert b is not None
                 if p[b] is None:
                     p[b] = [None, None]
@@ -84,7 +84,6 @@ def _parse_bit(self, x: object) -> None:
 
 
 class CCITTG4Parser(BitParser):
-
     MODE = [None, None]
     BitParser.add(MODE, 0, "1")
     BitParser.add(MODE, +1, "011")
@@ -475,9 +474,7 @@ def _do_vertical(self, dx: int) -> None:
             if x1 == 0:
                 if self._color == 1 and self._refline[x1] != self._color:
                     break
-            elif x1 == len(self._refline):
-                break
-            elif (
+            elif x1 == len(self._refline) or (
                 self._refline[x1 - 1] == self._color
                 and self._refline[x1] != self._color
             ):
@@ -501,9 +498,7 @@ def _do_pass(self) -> None:
             if x1 == 0:
                 if self._color == 1 and self._refline[x1] != self._color:
                     break
-            elif x1 == len(self._refline):
-                break
-            elif (
+            elif x1 == len(self._refline) or (
                 self._refline[x1 - 1] == self._color
                 and self._refline[x1] != self._color
             ):
@@ -513,9 +508,7 @@ def _do_pass(self) -> None:
             if x1 == 0:
                 if self._color == 0 and self._refline[x1] == self._color:
                     break
-            elif x1 == len(self._refline):
-                break
-            elif (
+            elif x1 == len(self._refline) or (
                 self._refline[x1 - 1] != self._color
                 and self._refline[x1] == self._color
             ):
@@ -550,7 +543,10 @@ def _do_uncompressed(self, bits: str) -> None:
 
 class CCITTFaxDecoder(CCITTG4Parser):
     def __init__(
-        self, width: int, bytealign: bool = False, reversed: bool = False
+        self,
+        width: int,
+        bytealign: bool = False,
+        reversed: bool = False,
     ) -> None:
         CCITTG4Parser.__init__(self, width, bytealign=bytealign)
         self.reversed = reversed
@@ -563,7 +559,7 @@ def output_line(self, y: int, bits: Sequence[int]) -> None:
         arr = array.array("B", [0] * ((len(bits) + 7) // 8))
         if self.reversed:
             bits = [1 - b for b in bits]
-        for (i, b) in enumerate(bits):
+        for i, b in enumerate(bits):
             if b:
                 arr[i // 8] += (128, 64, 32, 16, 8, 4, 2, 1)[i % 8]
         self._buf += arr.tobytes()
@@ -598,7 +594,7 @@ def __init__(self, width: int, bytealign: bool = False) -> None:
             self.img = pygame.Surface((self.width, 1000))
 
         def output_line(self, y: int, bits: Sequence[int]) -> None:
-            for (x, b) in enumerate(bits):
+            for x, b in enumerate(bits):
                 if b:
                     self.img.set_at((x, y), (255, 255, 255))
                 else: